Ollama Local AI

De-devs

O aplikaciji

🦙 Ollama Local AI — Local LLM, Cloud AI & WebUI, All On Your Device

🚀 Ollama Local AI is the ultimate companion for developers looking to integrate local Large Language Models (LLMs) seamlessly with their favorite IDE development workflows. Turn your Android device into a secure, ultra-fast, and switchable local-network OpenAI-compatible LLM proxy.

📱 Point Cursor, VS Code, Antigravity, Windsurf, or any modern coding assistant directly to your phone's LAN IP address and start using local models or API keys — without configuring multiple endpoints on your development machine.

🔒 100% On-Device: your models, keys, and data stay fully secure on your own device — no third-party service, no external relay.

⚡ Key Features

🧠 Local LLM On-Device: run models directly on your phone, no internet required

💬 Chat Mode: full chat sessions with local models or cloud APIs (OpenAI, Claude, and more) — switch anytime

🎨 Canvas Mode: build and test websites right inside chat, watch the AI construct it live

🌐 WebX Preview: instantly preview any website Ollama builds, viewable in any browser on any device on your network

🖥️ Cross-Device WebUI Access: open your chat WebUI from any device's browser — phone, tablet, or PC

🖥️ Zero-Config Local Hosting: spins up a highly optimized embedded HTTP server (NanoHTTPD) right on your Android phone

🔌 OpenAI-Compatible API: implements standard endpoints (/v1/chat/completions, /v1/models, /health) for drop-in compatibility

🔄 Instant Provider Switching: save configs for Ollama, NVIDIA, OpenAI, Claude, Hugging Face, custom endpoints — switch in one click

📊 Real-Time Traffic Visualizer: watch request flow, packet routing, and performance stats live

🔋 Lazy Token Bucket Rate Limiting: battery-efficient, zero background drain

🔐 Secure Encrypted Storage: API keys AES-256 encrypted (EncryptedSharedPreferences)

🧵 Offloaded I/O: fluid Compose UI, high-performance optimized routing via Coroutines + Dispatchers.IO

🛠️ Full IDE Support: high-performance optimized logic for Cursor, VS Code, Antigravity, Windsurf & more

🛣️ Coming Soon — Roadmap

🌐 Multi-Device Cluster Support: link multiple phones/devices into one local inference cluster

🧠 Orchestrator Mode: distribute compute across devices for more IDE power

⚙️ Many more logics, integrations & optimizations in development

❓ Why choose Ollama Local AI?
Chat, code, and preview — all powered by local or cloud AI, fully secured on your own device. Light, fast, unified, and private.

🔥 Optimize your LLM development today with Ollama Local AI!

Što je novo

Bug fixes and performance improvements.
Added local AI model downloads and on-device chat support.
Improved LAN proxy access for IDEs and OpenAI-compatible local endpoints.
Improved background service reliability, notifications, and app update flow.